I am an incoming Postdoctoral Associate at the Center for Global Women’s Health Technologies at Duke University. I recently earned my PhD in Electrical Engineering from UC San Diego (June 2025), where I was a Graduate Researcher in the Digital Health Technologies Lab under the supervision of Dr. Edward Wang. I am passionate about the intersection of human-machine interactions, engineering, and user-centered design. My research areas include Human-Computer Interaction (HCI), User-Centered Design, User Experience (UX), digital health systems, telehealth, and AI for women's health. My thesis aims to transform interactions between healthcare practitioners and stakeholders in telehealth consultations through an AI-mediated patient triaging system to facilitate lactation support. 

I have experience building interfaces for patient management systems (EHR) following healthcare regulations. In the Summer of 2022, I was a UX research intern at Qualcomm, working towards usability testing and how to reduce the effects of cybersickness in extended reality (XR) devices, integrating between UX and engineering teams for better systems. In the summer of 2018, I was a research intern at Microsoft Research in the clinical sensing and analytics group, working on techniques for racially fair PPG sensing on wrist-worn devices.

Research Interests and Values

• How can we leverage technological advances to provide specialized healthcare support in Latinx and low-income communities?

• Can AI-driven tools identify early breastfeeding complications, provide timely interventions, and improve breastfeeding duration and maternal well-being?

• How can we build better healthcare solutions to ensure equitable access to lactation support by people in need?

• How can researchers use their positions of influence to ensure technological innovations address critical challenges, such as those in the 2030 SDGs, for underserved minority communities?

Lactation-related nipple damage is a prevalent issue among breastfeeding mothers, often leading to early breastfeeding cessation due to pain and misdiagnosis. Accurate and timely classification of nipple damage is critical for effective treatment, yet current methods rely on subjective clinical assessments, resulting in variability and inefficiency. This study addresses these challenges by developing a Deep Learning (DL) system for the automated detection and classification of nipple damage. Using a dataset of 1,090 images from clinical trials developed in São Paulo, Brazil, we implemented a Resnet50 convolutional neural network (CNN) to perform two tasks: (1) binary classification to differentiate between intact nipples and those with damages and (2) multiclass classification to identify four types of damage (closed wound, crust, erosion, and fissure) based on the instrument for classifying nipple and areola complex lesions. Data augmentation techniques were applied to upsample the dataset to 8,720 images. The binary classification model achieved an average area under the receiver operating characteristics curve (AUROC) of 0.99 and a recall of 95.90%, demonstrating high accuracy in detecting nipple damage. The multiclass model achieved AUROC values ranging from 0.89 to 0.99 in nipple damage classification, with the highest performance observed for closed wounds (AUROC = 0.98) and erosion (AUROC = 0.99). Gradient-weighted Class Activation Mapping (Grad-CAM) visualizations confirmed the model’s focus on damaged areas, which aligned closely with clinical assessments. Our findings highlight the potential of DL to improve lactation care by enabling accurate, automated nipple damage classification, particularly in settings with limited access to lactation specialists. This study represents a significant step toward leveraging technology to address challenges in lactation care and improve outcomes for breastfeeding mothers.

NPJ Women's Health, under review

The postnatal period is a critical change for mothers, and is exacerbated by increased parental responsibilities and heavier cognitive loads. However, voice assistants (VAs) provide a promising potential in assisting mothers with postnatal care and managing child-related growth and developmental progress. To obtain an impression of where VA applications currently stand in the postnatal childcare sector and to establish the groundwork for forthcoming studies, we performed a thematic analysis of pertinent VA applications. We identified the features available and feature gaps, including recording medical information, statistical and graph analyses of child data, and childcare recommendations. Utilizing these discoveries, we suggest a VA tool that can track child-related health information, child-health reminders and alerts, and personalized recommendations for child development and growth. This paper provides an overview of the present condition of this area of study and highlights the need for additional research and advancements for better child development tracking.

ACM CUI 2025 - Extended Abstract

The postpartum period is a crucial time for physical and mental adjustment for a mother, which can worsen through increased demands and mental load. In Brazil, as in many Latin American countries, the unequal division of childcare responsibilities increases mothers’ risks of postpartum depression and anxiety while preventing mothers from focusing on their recovery. Voice assistants (VAs) are digital tools that can offer hands-free, on-demand support, potentially helping with childcare-related needs. Through a user-centered design approach, we conducted an online survey with 55 Brazilian mothers to investigate how VAs support postpartum mothers and their current usage in childcare-related tasks. We identified key challenges preventing VA technologies from effectively supporting Brazilian mothers, including language barriers, lack of personalized information retrieval, and missing features tailored to postpartum care and early childhood needs. We propose a set of design considerations for how VAs could meet mothers' needs for greater adoption in Brazil.

ACM CUI 2025 - Full Paper

Breast pain is one of the most common reasons for breastfeeding patients to reach out to their providers, seeking ways to mediate their pain and solve the issue. Our pain assessment application allows the patient to solicit remote guidance from their provider (i.e., lactation consultant (LC)) by informing details about their pain and providing an image of the wounded area. An AI pipeline analyzes the image for a quality check and pre-determines the possible condition of the patient, reporting this data to the healthcare provider and providing the patient temporary guidance to mitigate the issue while the patient waits for the provider’s contact. At the same time, the LC receives patient reports in order of severity so they know who to prioritize first.

ACM CHI 2024 - Extended abstracts

Current telehealth services help mothers seek Lactation Consultants (LCs) for breastfeeding support, where images help them identify and address many issues. Due to the disproportional ratio of LCs and mothers in need, these professionals are often overloaded and burned out. We investigate the effectiveness of a convolution neural network (CNN) in detecting healthy lactating breasts and six breastfeeding-related issues using only RGB images. Our goal is to assess the applicability of this algorithm as an auxiliary resource for LCs to manage their time more effectively, respond promptly to patient needs, and enhance the overall experience and care for breastfeeding mothers.

2024, JMIR AI

The limited adoption of Extended Reality (XR) Head-Mounted Devices (HMDs) due to device quality and cybersickness highlights the need for a deeper understanding of their impact on User Experience (UX). Previous studies evaluated visual perception, usability, and technical interventions as discrete elements. While some gather only quantitative measures, others gather qualitative measures at a more surface level. We propose a within-subjects mixed-methods evaluation to address these gaps to investigate hardware and software influences on user experience and task performance while wearing Video See-Through (VST) HMDs. This evaluation’s insights inform features that can improve device quality and user adoption across various domains.

2023, Frontiers in Virtual Reality

BPClip is a low-cost 3D-printed smartphone attachment for blood pressure monitoring that utilizes a smartphone's camera and flashlight. This device aims to make blood pressure measurement more accessible, particularly in resource-limited settings. By promoting the use of this affordable technology, the intention is to facilitate better management of hypertension and overall health for individuals worldwide.

2023, Nature Scientific Reports

Lactation consultants (LCs) positively impact chestfeeding rates by providing in-person support to struggling parents. In Brazil, LCs are a scarce resource and in high demand, risking chestfeeding rates across many communities nationwide. The transition to remote consultations during the COVID-19 pandemic made LCs face several challenges in solving chestfeeding problems due to limited technical resources for management, communication, and diagnosis. This study investigates the main technological issues LCs have in remote consultations and what technology features are helpful for chestfeeding problem-solving in remote settings.

2023, Frontiers in Digital Health

Long-term breastfeeding has been shown to exhibit several environmental benefits and health benefits for both the mother and baby. Despite the known advantages, several mothers choose not to maintain breastfeeding long-term. How long a mother breastfeeds is heavily influenced by lactation and latching, and so the mother’s critical point of support is the lactation consultant (LC), who guides and provides instruction for creating a more positive breastfeeding experience. Empowering lactation consultants with methods to deliver instruction and support remotely is essential for advancing telehealth and wide-scale adoption. This paper presents findings from a need-finding study of 6 LC’s that sheds light on ways to address some of the challenges faced by the LC community when providing remote lactation support. 

ACM CHI 2022 - Extended abstracts

A photoplethysmogram device is provided comprising a light source configured to emit light to illuminate skin, a photo-detector configured to receive the light illuminating the skin and generate an electrical output as a function of an intensity of the received light, a skin temperature regulator configured to heat and/or cool a temperature of the skin adjacent to the photo-detector and light source to increase the signal-to-noise ratio (SNR) of the electrical output from the photo-detector, and a processor configured to generate, based on the electrical output, an output signal indicative of blood properties, including physiological parameters such as blood pressure, heart rate, stroke volume, cardiac output, total peripheral resistance, blood vessel elasticity, and arterial oxygen saturation.